# Model library

> The Myles model library: every Myles model, where it runs (GPU, CPU or browser), its median speed, and how to call or license it.

Section: Models. Web page: https://www.launchables.ai/docs/models

One family, one job: the decision. Every Myles model reads a state, a question and options and returns a probability for every option; none writes text. Myles-G is called over HTTP; the CPU models run in your own program. Pick the size for the hardware you have, then see [Model types](https://www.launchables.ai/docs/model-types) for how to call it.

- [**Myles-G**: The hardest decisions, on our API or one GPU you own.](https://www.launchables.ai/docs/models#myles-g)
- [**CPU models**: Myles-400M, 150M and 22M: servers, laptops, phones and browsers.](https://www.launchables.ai/docs/models#cpu-models)

## Complete library

| Model | Runs on | Median | How you call it | Available as | Status |
|---|---|---|---|---|---|
| **Myles-G 31B** | One data-centre GPU | 48 ms | [`POST /v1/decide`](https://www.launchables.ai/docs/model-types#gpu) | Hosted API · your hardware | Available |
| **Myles-G 12B** | One workstation GPU | 31 ms | [`POST /v1/decide`](https://www.launchables.ai/docs/model-types#gpu) | Hosted API · your hardware | Available |
| **Myles-G Edge** | Laptop- and phone-class GPUs | 21 ms | [`POST /v1/decide`](https://www.launchables.ai/docs/model-types#gpu) | Your hardware | By request |
| **Myles-400M** | The cheapest server you have | about 500 ms | [`decide()` in Python](https://www.launchables.ai/docs/model-types#cpu) | Your hardware · evaluation weights | Available |
| **Myles-150M** | A laptop | 196 ms | [`decide()` in Python](https://www.launchables.ai/docs/model-types#cpu) | Your hardware · evaluation weights | Available |
| **Myles-22M** | A browser or a phone | 27 ms | [`decide()` in Python](https://www.launchables.ai/docs/model-types#cpu) | Your hardware · evaluation weights · in the browser | Available |

Median time for one decision: Myles-G on one GPU; the CPU models on one thread of a desktop processor. "Your hardware" is under a licence per deployment; see [Licensing](https://www.launchables.ai/licensing) or [request a self-hosted evaluation](https://www.launchables.ai/contact?about=evaluation).

## Myles-G

Myles-G is for the hardest decisions. Launchables trains it for decisions only, and it runs on one GPU with no customer data leaving your premises. Myles-G 12B and Myles-G 31B are available on the [hosted API](https://www.launchables.ai/docs/deploy/hosted); every Myles-G model is available by request on your own hardware. Every Myles-G model is called the same way: `POST /v1/decide` with a state and typed questions ([API reference](https://www.launchables.ai/docs/api/decide)). Myles-G 12B and Myles-G 31B also read images sent with the request ([Images](https://www.launchables.ai/docs/api/images)).

On the 231 public JevBench items, Myles-G 31B answers 211, 12B 203 and Edge 189. Unverified: our own measurement, of the builds our API serves for the 31B and 12B (16 October 2026; the 31B reads 210 to 212 across server restarts) and of Edge on 11 October 2026; not an official placement, and official evaluation pending. Myles-G is adapted from Google's openly licensed Gemma 4 (Apache 2.0); Gemma is a trademark of Google LLC.

## CPU models

Myles-400M, 150M and 22M need no GPU and run on disconnected networks. Myles-400M is 91.8% correct on our frozen set of 1,400 held-out decisions, on one CPU thread (measured on the September 2026 Myles-400M build). Organisations can request the weights of all three for internal evaluation on Hugging Face: [Myles-400M](https://huggingface.co/launchables/myles-400m), [Myles-150M](https://huggingface.co/launchables/myles-150m) and [Myles-22M](https://huggingface.co/launchables/myles-22m). We review every request. Myles-22M runs in a browser: [try it](https://www.launchables.ai/developers) or read its [model card](https://www.launchables.ai/models/myles-22m). The CPU models have no HTTP API: you load the model file in your own program and call `decide(state, question, options)`, which returns a probability per option ([example](https://www.launchables.ai/docs/model-types#cpu)).

## Lineage

Every new Myles model ships with a record of its base model, data and licences. Our standard: no Chinese-origin models or data anywhere in the lineage, and no outputs of hosted models as training data. See [What is in a lineage record](https://www.launchables.ai/notes/lineage-record).